AI葵

First to answer your question: > we use the neural networks to get the 4d volume this part is slow. The rendering part is very fast. Your idea is partly...

It cannot generate good result on the top part of the object because training images don't contain much of that region. One thing you can try is to modify the...

Yes, so regarding the question of the op, to remove the noisy cloud in the synthesized image, one should change this 0.1, 0.2, 0.3 vector to make the camera point...

Are you talking about poses? You can generate poses (the relative position and rotation of the camera for the images) by following [here](https://github.com/bmild/nerf#generating-poses-for-your-own-scenes). The xyz and direction is for **each...

See [this issue](https://github.com/bmild/nerf/issues/30) The method he takes for synthetic object is to predefine a fixed grid volume, and predict each grid point is occupied or not. This method is practically...

Yes it's also applicable for real inward-facing scenes, but definitely not for forward facing scenes where you have HUGE space.

The color depends on the viewing direction; I think the author wants to highlight this fact that he didn't add color to the 3d model. You might be able to...

I wrote code to generate **colored** mesh in [my implementation](https://github.com/kwea123/nerf_pl/blob/master/README_mesh.md), will add a video explanation these days.

LLFF script just converts colmap result (either gui or command line) to another format that nerf can parse. When you say "using colmap gui", how did you convert to input...

In practice for LLFF dataset, the space viewed by other frustums might slightly go over the averaged frustum, but only a little (e.g. ~+-1.2), so it doesn't pose any problem...